Implementation of Scale and Rotation Invariant On-Line Object Tracking Based on CUDA
スポンサーリンク
概要
- 論文の詳細を見る
Object tracking is a major technique in image processing and computer vision. Tracking speed will directly determine the quality of applications. This paper presents a parallel implementation for a recently proposed scale- and rotation-invariant on-line object tracking system. The algorithm is based on NVIDIA's Graphics Processing Units (GPU) using Compute Unified Device Architecture (CUDA), following the model of single instruction multiple threads. Specifically, we analyze the original algorithm and propose the GPU-based parallel design. Emphasis is placed on exploiting the data parallelism and memory usage. In addition, we apply optimization technique to maximize the utilization of NVIDIA's GPU and reduce the data transfer time. Experimental results show that our GPGPU-based method running on a GTX480 graphics card could achieve up to 12X speed-up compared with the efficiency equivalence on an Intel E8400 3.0GHz CPU, including I/O time.
- 2011-12-01
著者
-
Wang Guijin
Dept. Of Electronic Engineering Tsinghua University
-
Lin Xinggang
Department Of Electronic Engineering Tsinghua University
-
MIAO Quan
Department of Electronic Engineering, Tsinghua University
-
Miao Quan
Department Of Electronic Engineering Tsinghua University
-
Wang Guijin
Department Of Electronic Engineering Tsinghua University
関連論文
- Online HOG Method in Pedestrian Tracking
- Robust Object Tracking via Combining Observation Models
- A Framework of Real Time Hand Gesture Vision Based Human-Computer Interaction
- Measuring Particles in Joint Feature-Spatial Space
- A Flow-Aware Opportunistic Routing Protocol for Wireless Mesh Networks
- Kernel Based Image Registration Incorporating with Both Feature and Intensity Matching
- Real-Time Human Detection Using Hierarchical HOG Matrices
- DSP-Based Parallel Implementation of Speeded-Up Robust Features
- Non-rigid Object Tracking as Salient Region Segmentation and Association
- Partial Derivative Guidance for Weak Classifier Mining in Pedestrian Detection
- Drastic Anomaly Detection in Video Using Motion Direction Statistics
- High-Accuracy Sub-Pixel Registration for Noisy Images Based on Phase Correlation
- Stereo Matching Using Local Plane Fitting in Confidence-Based Support Window
- Implementation of Scale and Rotation Invariant On-Line Object Tracking Based on CUDA
- A Real-Time Human Detection System for Video
- An Interleaving Updating Framework of Disparity and Confidence Map for Stereo Matching
- Self-Clustering Symmetry Detection
- High-Accuracy and Quick Matting Based on Sample-Pair Refinement and Local Optimization
- Kernel-Based On-Line Object Tracking Combining both Local Description and Global Representation